amazing work,can it support that generate the phoneme delayed time sequence?

myshell-ai / MeloTTS

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

MIT License

4.84k stars 631 forks source link

amazing work,can it support that generate the phoneme delayed time sequence? #168

Open CasonTsai opened 3 months ago

CasonTsai commented 3 months ago

it's a great work, is it support that generate the phoneme delayed time sequence ?or is there any tool we can get the phoneme delayed(duration) time sequence?

Zengyi-Qin commented 3 months ago

Hi - Currently this is not supported in MeloTTS. You can try this https://montreal-forced-aligner.readthedocs.io/en/latest/

CasonTsai commented 3 months ago

Hi - Currently this is not supported in MeloTTS. You can try this https://montreal-forced-aligner.readthedocs.io/en/latest/

Sorry, I expressed it wrongly。i see there is a StochasticDurationPredictor in meloTTS，so i want know to wether we can get the phoneme duration time according to output of StochasticDurationPredictor in inference?